Determination of exact rotation angle and discrimination for rotated images

Determination of exact rotation angle and discrimination for rotated images

The complex frequency scaling property of Fourier transforms may be very effective for the determination of exact image rotation angle in application areas such as defense, manufacturing agriculture and commerce. In this paper, we exploit the complex frequency scaling property of Fourier transform t...

Full description

Saved in:
Bibliographic Details
Published in:Optics and laser technology Vol. 34; no. 4; pp. 313 - 327
Main Authors: Iftekharuddin, K.M., Rentala, C., Dani, A.
Format: Journal Article
Language:English
Published: Oxford Elsevier Ltd 01-06-2002
Elsevier Science
Subjects:
Automatic target recognition (ATR)
Edge detection
Exact sciences and technology
Feature extraction
Fourier transform
Fundamental areas of phenomenology (including applications)
Hilbert transform
Image forming and processing
Image processing
Imaging and optical processing
Optics
Pattern recognition
Physics
Synthetic aperture radar (SAR) image
Hilbert transform
Image processing
Synthetic aperture radar (SAR) image
Fourier transform
Feature extraction
Pattern recognition
Automatic target recognition (ATR)
Edge detection
Fourier transformation
Algorithms
Gray scale
Theoretical study
Synthetic-aperture radar
Rotation angle
Target detection
Hilbert transformation
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The complex frequency scaling property of Fourier transforms may be very effective for the determination of exact image rotation angle in application areas such as defense, manufacturing agriculture and commerce. In this paper, we exploit the complex frequency scaling property of Fourier transform to determine the exact angle of rotation of a target image with respect to reference image. We also investigate the validity of the developed algorithm using occluded target images. Further, we extend our algorithm to differentiate between different but similar rotated target images. We use both gray scale and DARPA's moving and stationary target recognition program's synthetic aperture radar images to validate our algorithm.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0030-3992
1879-2545
DOI:10.1016/S0030-3992(02)00020-8